Aircraft windshield crack detection modeling method, device and equipment and storage medium

Abstract

The invention discloses an aircraft windshield crack detection modeling method, device and equipment and a storage medium. Crack detection is performed on a target windshield through an ultrasonic detection technology; if the crack exists on the target windshield, determining a crack area and crack depth data on the target windshield; collecting top view image data corresponding to the crack area, inputting the top view image data and the crack depth data into a trained machine learning model, and identifying the crack projection position through the machine learning model to obtain a corresponding crack projection position identification result; and according to the standard module data, the crack area, the crack depth data and the crack projection position identification result corresponding to the target windshield, modeling the crack of the target windshield to obtain a modeling result. According to the method, the precision of crack detection can be improved, the presentation effect of the detection result can be improved, more valuable information can be provided for maintenance treatment, and the practicability of crack detection is improved. The method can be widely applied to the technical field of airplanes.

Description

Technical Field

[0001] The present application relates to the field of aircraft technology, and in particular to a detection modeling method, device, equipment and storage medium for aircraft windshield cracks. Background Art

[0002] An airplane is an aircraft that can fly in the atmosphere. It usually relies on the lift generated by its wings to support the weight of the fuselage and uses the thrust or pull provided by the engine to move forward. An airplane windshield refers to the transparent glass installed in front of the cockpit of an airplane. It is usually composed of multiple layers of materials. Its main function is to protect pilots and passengers from airflow, rain, hail and other external factors, while also being able to withstand pressure and temperature changes during high-speed flight. Due to the complex flight conditions, cracks may appear on the airplane windshield, and cracks need to be detected and analyzed to facilitate the determination of corresponding maintenance and treatment strategies.

[0003] In the related art, when crack detection is performed on an aircraft windshield, relevant detection equipment is often used to detect cracks one by one. The detection results obtained can only indicate whether there are cracks, but it is difficult to clearly display the specific conditions of the cracks. The detection accuracy is low, and it is difficult to provide valuable information for maintenance and processing, and the practicality is poor. Summary of the invention

[0004] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0005] To this end, an object of an embodiment of the present application is to provide a detection modeling method, device, equipment and storage medium for aircraft windshield cracks.

[0006] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0007] On the one hand, an embodiment of the present application provides a detection modeling method for aircraft windshield cracks, the method comprising:

[0008] Detect cracks on target windshields using ultrasonic detection technology;

[0009] If cracks exist on the target windshield, determine crack area and crack depth data on the target windshield;

[0010] Collecting overhead image data corresponding to the crack area, inputting the overhead image data and the crack depth data into a trained machine learning model, identifying the crack projection position through the machine learning model, and obtaining a corresponding crack projection position identification result;

[0011] The crack of the target windshield is modeled according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

[0012] In addition, the aircraft windshield crack detection modeling method according to the above embodiment of the present application may also have the following additional technical features:

[0013] Further, in one embodiment of the present application, the target windshield includes a first inorganic glass layer, a second inorganic glass layer, and an organic glass layer;

[0014] The first surface of the first inorganic glass layer is the outer surface of the target windshield, the second surface of the first inorganic glass layer is in contact with the first surface of the organic glass layer, the second surface of the organic glass layer is in contact with the first surface of the second inorganic glass layer, and the second surface of the second inorganic glass layer is the inner surface of the target windshield.

[0015] Further, in one embodiment of the present application, the crack detection of the target windshield by ultrasonic detection technology includes:

[0016] Sending ultrasonic waves to any detection area on the target windshield, and receiving echo data corresponding to the ultrasonic waves;

[0017] If the echo data is disordered, determining that the target windshield has a crack in the detection area;

[0018] The target surface where the crack is located is determined according to the time node at which the echo data is disturbed.

[0019] Further, in one embodiment of the present application, determining the crack depth data on the target windshield includes:

[0020] If the target surface is the first surface of the first inorganic glass layer, obtaining a first time duration corresponding to the propagation of the ultrasonic wave in the crack on the first surface of the first inorganic glass layer;

[0021] The crack depth data is determined according to the product of the first time length and a reference propagation speed of the ultrasonic wave in the air.

[0022] Further, in one embodiment of the present application, determining the crack depth data on the target windshield includes:

[0023] If the target surface is the first surface of the organic glass layer, obtain the second thickness data of the organic glass layer, the second propagation speed of the ultrasonic wave in the organic glass layer, the reference propagation speed of the ultrasonic wave in the air, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, the total reference time length of the ultrasonic wave passing through the template windshield, and the total time length of the ultrasonic wave passing through the target windshield; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks;

[0024] A first set of equations is established, wherein the formula of the first set of equations is:

[0025] H2=v0*t 21 +v2*t 22

[0026] t 21 +t 22 -t2=t 总 -t

[0027] Wherein, H2 represents the second thickness data of the organic glass layer, v0 represents the reference propagation speed of the ultrasonic wave in the air, and t 21 represents the second time duration corresponding to the ultrasonic wave propagating in the crack on the first surface of the organic glass layer, v2 represents the second propagation speed of the ultrasonic wave in the organic glass layer, t 22 represents the third time duration corresponding to the propagation of the ultrasonic wave in the organic glass layer except for the cracks, t2 represents the second reference time duration of the ultrasonic wave passing through the organic glass layer of the template windshield, t 总 represents the total reference time length of the ultrasonic wave passing through the template windshield, and t represents the total time length of the ultrasonic wave passing through the target windshield;

[0028] Solving the first set of equations to obtain the second time length;

[0029] The crack depth data is determined according to the second time length and a reference propagation speed of the ultrasonic wave in the air.

[0030] Further, in one embodiment of the present application, determining the crack depth data on the target windshield includes:

[0031] If the target surface is the second surface of the second inorganic glass layer, obtain the third thickness data of the second inorganic glass layer, the third propagation speed of the ultrasonic wave in the second inorganic glass layer, the first reference time length of the ultrasonic wave passing through the first inorganic glass layer, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, and the total time length of the ultrasonic wave passing through the target windshield; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks;

[0032] Calculate the total duration minus the difference between the first reference duration and the second reference duration to obtain a fourth duration;

[0033] Obtain fourth thickness data according to the product of the fourth time length and the third propagation speed;

[0034] The difference between the third thickness data and the fourth thickness data is calculated to obtain the crack depth data.

[0035] On the other hand, an embodiment of the present application provides a detection and modeling device for aircraft windshield cracks, the device comprising:

[0036] A detection unit, used for performing crack detection on a target windshield by using ultrasonic detection technology;

[0037] a processing unit, configured to determine crack area and crack depth data on the target windshield if cracks exist on the target windshield;

[0038] An identification unit is used to collect overhead image data corresponding to the crack area, input the overhead image data and the crack depth data into a trained machine learning model, identify the crack projection position through the machine learning model, and obtain a corresponding crack projection position identification result;

[0039] The integration unit is used to model the crack of the target windshield according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

[0040] Further, in one embodiment of the present application, the target windshield includes a first inorganic glass layer, a second inorganic glass layer, and an organic glass layer;

[0041] The first surface of the first inorganic glass layer is the outer surface of the target windshield, the second surface of the first inorganic glass layer is in contact with the first surface of the organic glass layer, the second surface of the organic glass layer is in contact with the first surface of the second inorganic glass layer, and the second surface of the second inorganic glass layer is the inner surface of the target windshield.

[0042] On the other hand, an embodiment of the present application provides a computer device, including:

[0043] at least one processor;

[0044] at least one memory for storing at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned aircraft windshield crack detection modeling method.

[0046] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned aircraft windshield crack detection modeling method.

[0047] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0048] The embodiment of the present application discloses a detection modeling method for cracks on an aircraft windshield, which detects cracks on a target windshield through ultrasonic detection technology; if cracks exist on the target windshield, the crack area and crack depth data on the target windshield are determined; the overhead image data corresponding to the crack area is collected, and the overhead image data and the crack depth data are input into a trained machine learning model, and the crack projection position is identified through the machine learning model to obtain a corresponding crack projection position identification result; according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result, the crack of the target windshield is modeled to obtain a modeling result. The method can integrate the crack area, crack depth data and crack projection position information on the aircraft windshield to achieve modeling processing for cracks, improve the accuracy of crack detection and improve the presentation effect of detection results, so as to provide more valuable information for maintenance processing and improve the practicality of crack detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 A schematic diagram of an implementation environment of a detection modeling method for aircraft windshield cracks provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a flow chart of a detection modeling method for aircraft windshield cracks provided in an embodiment of the present application;

[0052] Figure 3A schematic diagram of top-view image data of a crack provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a crack projection position provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of an aircraft windshield provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram showing cracks on a first surface of a first inorganic glass layer provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram showing cracks on a first surface of an organic glass layer provided in an embodiment of the present application;

[0057] Figure 8 A schematic diagram showing cracks on the second surface of a second inorganic glass layer provided in an embodiment of the present application;

[0058] Fig. 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0060] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0063] 1) Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0064] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. Basic artificial intelligence technologies generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, pre-trained models are also called large models and basic models. After fine-tuning, they can be widely used in downstream tasks in various major directions of artificial intelligence. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0065] 2) Machine Learning (ML) is a multi-disciplinary interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning. The pre-trained model is the latest development in deep learning, which integrates the above technologies.

[0066] 3) Crack projection position: Lay the aircraft windshield flat downward and look down at the projection of the deepest point of each windshield crack on the plane. This is the crack projection position.

[0067] An airplane is an aircraft that can fly in the atmosphere. It usually relies on the lift generated by its wings to support the weight of the fuselage and uses the thrust or pull provided by the engine to move forward. An airplane windshield refers to the transparent glass installed in front of the cockpit of an airplane. It is usually composed of multiple layers of materials. Its main function is to protect pilots and passengers from airflow, rain, hail and other external factors, while also being able to withstand pressure and temperature changes during high-speed flight. Due to the complex flight conditions, cracks may appear on the airplane windshield, and cracks need to be detected and analyzed to facilitate the determination of corresponding maintenance and treatment strategies.

[0068] In the related art, when crack detection is performed on an aircraft windshield, relevant detection equipment is often used to detect cracks one by one. The detection results obtained can only indicate whether there are cracks, but it is difficult to clearly display the specific conditions of the cracks. The detection accuracy is low, and it is difficult to provide valuable information for maintenance and processing, and the practicality is poor.

[0069] In view of this, a detection modeling method for cracks on an aircraft windshield is provided in an embodiment of the present application. The target windshield is cracked by ultrasonic detection technology; if cracks exist on the target windshield, the crack area and crack depth data on the target windshield are determined; the overhead image data corresponding to the crack area is collected, and the overhead image data and the crack depth data are input into a trained machine learning model, and the crack projection position is identified by the machine learning model to obtain a corresponding crack projection position identification result; the crack of the target windshield is modeled according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result. The method can realize the modeling processing of cracks by integrating the crack area, crack depth data and crack projection position information on the aircraft windshield, and can improve the accuracy of crack detection and the presentation effect of the detection results, so as to provide more valuable information for maintenance processing and improve the practicality of crack detection.

[0070] Reference Figure 1 , Figure 1 The schematic diagram of the implementation environment of a detection modeling method for aircraft windshield cracks provided in the embodiment of the present application is shown. In the implementation environment, the main software and hardware entities involved include a terminal device 110 and a background server 120.

[0071] In the embodiment of the present application, a relevant application may be installed in the terminal device 110, and the application may be used to implement the detection modeling of the cracks on the aircraft windshield. The background server 120 may be the background server of the application. The terminal device 110 and the background server 120 may be connected to each other in communication, and the background server 120 may be used to process the business data related to the application, and implement the related application functions through the interaction with the terminal device 110. The detection modeling method of the cracks on the aircraft windshield provided in the embodiment of the present application may be implemented by the terminal device 110 alone, or may be implemented based on the interaction between the terminal device 110 and the background server 120.

[0072] The terminal device 110 in the above embodiments may include a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart watch, and a vehicle-mounted terminal, but is not limited thereto.

[0073] The backend server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0074] The terminal device 110 and the backend server 120 may establish a communication connection through a wireless network or a wired network. The wireless network or wired network uses standard communication technology and / or protocols, and the network may be set to the Internet, or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network. Moreover, the above-mentioned software and hardware entities may use the same communication connection mode or different communication connection modes, and this application does not impose any specific restrictions on this.

[0075] Of course, it is understandable that Figure 1 The implementation environment in the embodiment of the present application is only some optional application scenarios of the detection modeling method of the aircraft windshield crack provided in the embodiment of the present application, and the actual application is not fixed to Figure 1 The hardware and software environment shown.

[0076] Next, in combination with the introduction of the aforementioned implementation environment, a detection modeling method for aircraft windshield cracks provided in an embodiment of the present application is introduced and illustrated.

[0077] Please refer to Figure 2 , Figure 2 is a flow chart of a detection modeling method for aircraft windshield cracks provided in an embodiment of the present application, with reference to Figure 2 The detection modeling method of an aircraft windshield crack includes but is not limited to:

[0078] Step 210: Perform crack detection on the target windshield by using ultrasonic detection technology;

[0079] Step 220: If cracks exist on the target windshield, determine the crack area and crack depth data on the target windshield;

[0080] Step 230: collecting overhead image data corresponding to the crack area, inputting the overhead image data and the crack depth data into a trained machine learning model, identifying the crack projection position through the machine learning model, and obtaining a corresponding crack projection position identification result;

[0081] Step 240: Model the crack of the target windshield according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

[0082] In an embodiment of the present application, a detection modeling method for aircraft windshield cracks is provided. The method can integrate the crack area, crack depth data and crack projection position information on the aircraft windshield to achieve modeling processing for the cracks, which can improve the accuracy of crack detection and improve the presentation of detection results, thereby facilitating the provision of more valuable information for maintenance processing and improving the practicability of crack detection.

[0083] In the embodiment of the present application, ultrasonic detection technology and machine learning methods are used to detect and model cracks in aircraft windshields. Specifically, the windshield to be detected is recorded as the target windshield. First, the windshield can be scanned using an ultrasonic probe to detect whether there is a crack. Ultrasonic detection is a non-destructive detection method that can effectively detect defects inside the material, such as cracks. If a crack is detected, the location area of ​​the crack on the target windshield can be further determined, and in the embodiment of the present application, it is recorded as a crack area. For example, in some embodiments, the target windshield can be divided into multiple areas to be detected in advance, and then an ultrasonic probe is used to detect each area in turn. If a crack is found in a certain area, it can be determined as a crack area. Alternatively, in some embodiments, detection can also be performed in the form of position points. When a certain position point is determined as a crack position point, the area near the position point can be determined as a crack area. In the embodiment of the present application, there is no restriction on the specific size and shape of the crack area.

[0084] When it is determined that there is a crack, in the embodiment of the present application, the crack depth data corresponding to the crack can also be determined. Then, the overhead image data corresponding to the crack area can be collected, and the overhead image data and the crack depth data can be input into the trained machine learning model. The crack projection position can be identified by the machine learning model to obtain the corresponding crack projection position identification result.

[0085] In the embodiment of the present application, the crack projection position is the line segment formed by the deepest point of the crack. For example, please refer to Figure 3 , Figure 3 FIG. 1 is a schematic diagram of top view image data of a crack provided in an embodiment of the present application. Figure 3 It can be seen that in the top-view image data, the crack is an area as a whole. Although the image can reflect the shape characteristics of the crack to a certain extent, the specific direction of the gully inside the crack is difficult to intuitively obtain. Therefore, in the embodiment of the present application, the top-view image data of the crack and the crack depth data can be combined and processed using a machine learning model to identify the specific bottom position point, thereby obtaining information on the crack projection position. Please refer to Figure 4 , Figure 4 A schematic diagram showing a crack projection position provided in an embodiment of the present application is shown, Figure 4 The crack projection position in Figure 3 It can be seen from the top-view image data that the crack projection position can clearly indicate the direction of the gully at the deepest point of the crack, which can facilitate the determination of the specific structure of the crack, thereby providing more valuable information for maintenance and treatment and improving the practicality of crack detection.

[0086] In the embodiments of the present application, in the task of identifying the projection position of the crack, various types of machine learning models can be selected, and the present application does not limit the specific types. For example, in some embodiments, convolutional neural networks (CNNs) can be used, and convolutional neural networks perform well in processing image data, especially in feature extraction and pattern recognition. In some embodiments, deep learning models can also be selected. Deep learning models (such as deep neural networks) can automatically learn high-level abstract features and are very suitable for processing complex data sets. For machine learning models, they need to be trained before use to achieve better performance. In the embodiments of the present application, some sample data can be used, such as overhead image data of a cracked windshield and crack depth data of the crack, and the crack projection position therein can be annotated. Based on these sample data, the training of the machine learning model can be achieved.

[0087] After obtaining the crack area, crack depth data and crack projection position identification results of the target windshield, the crack of the target windshield can be modeled in combination with the standard module data corresponding to the target windshield to obtain a modeling result. Here, the standard module data corresponding to the target windshield can record the shape of the target windshield without cracks and related parameter information, which can be established in advance. For example, based on the template windshield corresponding to the target windshield, the standard module data can be established by scanning the template windshield at multiple angles. The template windshield is the same model as the target windshield and does not have cracks. In the embodiment of the present application, the modeling result can comprehensively and accurately display the crack situation in the target windshield and improve the presentation effect of the detection results.

[0088] It can be understood that the detection modeling method of cracks on the aircraft windshield provided in the embodiment of the present application performs crack detection on the target windshield through ultrasonic detection technology; if there is a crack on the target windshield, the crack area and crack depth data on the target windshield are determined; the overhead image data corresponding to the crack area is collected, and the overhead image data and the crack depth data are input into the trained machine learning model, and the crack projection position is identified by the machine learning model to obtain the corresponding crack projection position identification result; according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result, the crack of the target windshield is modeled to obtain the modeling result. This method can realize the modeling processing of cracks by integrating the crack area, crack depth data and crack projection position information on the aircraft windshield, which can improve the accuracy of crack detection and improve the presentation effect of detection results, so as to provide more valuable information for maintenance processing and improve the practicality of crack detection.

[0089] Specifically, in some embodiments, the target windshield includes a first inorganic glass layer, a second inorganic glass layer, and an organic glass layer;

[0090] The first surface of the first inorganic glass layer is the outer surface of the target windshield, the second surface of the first inorganic glass layer is in contact with the first surface of the organic glass layer, the second surface of the organic glass layer is in contact with the first surface of the second inorganic glass layer, and the second surface of the second inorganic glass layer is the inner surface of the target windshield.

[0091] In the embodiment of the present application, the target windshield may be composed of three layers of glass, specifically including a first inorganic glass layer, a second inorganic glass layer and an organic glass layer. Figure 5 , Figure 5A schematic diagram of an aircraft windshield provided in an embodiment of the present application is shown. In the embodiment of the present application, the first surface of the first inorganic glass layer 510 is the outer surface of the target windshield, the second surface is bonded to the organic glass layer 520, the other surface of the organic glass layer 520 is bonded to the second inorganic glass layer 530, and the other surface of the second inorganic glass layer 530 is the inner surface of the target windshield. The thickness of the first inorganic glass layer 510 can be recorded as H1, the thickness of the organic glass layer 520 can be recorded as H2, and the thickness of the third inorganic glass layer 530 can be recorded as H3.

[0092] Specifically, in some embodiments, the method of performing crack detection on the target windshield by using ultrasonic detection technology includes:

[0093] Sending ultrasonic waves to any detection area on the target windshield, and receiving echo data corresponding to the ultrasonic waves;

[0094] If the echo data is disordered, determining that the target windshield has a crack in the detection area;

[0095] The target surface where the crack is located is determined according to the time node at which the echo data is disturbed.

[0096] In the embodiment of the present application, when crack detection is performed on the target windshield, an ultrasonic wave can be sent to any detection area therein, and echo data corresponding to the ultrasonic wave can be received. Ultrasonic waves are sound waves with a frequency higher than the human hearing range, usually above 20kHz. It propagates at different speeds in different media, but it propagates faster in air and most solid materials. When the ultrasonic pulse propagates inside the windshield, it will encounter different interfaces (such as air-glass interface, glass-crack interface, etc.) and reflect back on these interfaces. The receiver will capture these echo signals and record their time and intensity information. These data constitute the echo data. The collected echo data will be analyzed. Under normal circumstances, if there are no cracks or other defects, the echo data should show a certain regularity. If there are cracks, the interface reflection at the crack will cause the echo data to be abnormal, which is manifested as disorder in the intensity, time and shape of the echo signal. By analyzing the echo data, if obvious disorder is found, it can be judged that there is a crack in the corresponding detection area. In addition, the approximate location of the crack can be inferred based on the time point when the echo signal is disordered. This is because the propagation speed of ultrasound in different media is known. By calculating the time difference for the echo signal to reach the receiver, the distance between the crack and the transmitter can be estimated. Furthermore, based on the characteristics of the echo signal caused by the crack, it is possible to determine which surface of the windshield the crack is located on. In this embodiment of the present application, it can be recorded as the target surface.

[0097] Specifically, in some embodiments, determining crack depth data on the target windshield includes:

[0098] If the target surface is the first surface of the first inorganic glass layer, obtaining a first time duration corresponding to the propagation of the ultrasonic wave in the crack on the first surface of the first inorganic glass layer;

[0099] The crack depth data is determined according to the product of the first time length and a reference propagation speed of the ultrasonic wave in the air.

[0100] In the present application, refer to Figure 6 , Figure 6 A schematic diagram showing a crack on the first surface of the first inorganic glass layer is shown. If the target surface is the first surface of the first inorganic glass layer, the total thickness of the first inorganic glass layer is H1, wherein the thickness of the cracked portion is H 11 , i.e., crack depth data. In the embodiment of the present application, the time duration corresponding to the propagation of the ultrasonic wave in the crack on the first surface of the first inorganic glass layer can be obtained, which is recorded as the first time duration. Specifically, in general, if there is no crack in the first inorganic glass layer, the position where the echo data is first disturbed will be between the first inorganic glass layer and the organic glass layer. It is easy to understand that when there is a crack on the first surface of the first inorganic glass layer, the time node of the corresponding echo data disorder will be greatly advanced. Therefore, when obtaining the first time duration, the time node when the echo data is first disturbed can be referred to. If the time node is consistent with the situation that there is no crack in the first inorganic glass layer, it means that there is no crack in the first inorganic glass layer. If the time node is advanced relative to the situation that there is no crack in the first inorganic glass layer, it means that there is a crack in the first inorganic glass layer, and the first time duration can be directly determined according to the time node. Then, the crack depth data can be determined according to the product of the first time duration and the reference propagation speed of the ultrasonic wave in the air.

[0101] Specifically, in some embodiments, determining crack depth data on the target windshield includes:

[0102] If the target surface is the first surface of the organic glass layer, obtain the second thickness data of the organic glass layer, the second propagation speed of the ultrasonic wave in the organic glass layer, the reference propagation speed of the ultrasonic wave in the air, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, the total reference time length of the ultrasonic wave passing through the template windshield, and the total time length of the ultrasonic wave passing through the target windshield; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks;

[0103] A first set of equations is established, wherein the formula of the first set of equations is:

[0104] H2=v0*t 21 +v2*t 22

[0105] t 21 +t 22 -t2=t 总 -t

[0106] Wherein, H2 represents the second thickness data of the organic glass layer, v0 represents the reference propagation speed of the ultrasonic wave in the air, and t 21 represents the second time duration corresponding to the ultrasonic wave propagating in the crack on the first surface of the organic glass layer, v2 represents the second propagation speed of the ultrasonic wave in the organic glass layer, t 22 represents the third time duration corresponding to the propagation of the ultrasonic wave in the organic glass layer except for the cracks, t2 represents the second reference time duration of the ultrasonic wave passing through the organic glass layer of the template windshield, t 总 represents the total reference time length of the ultrasonic wave passing through the template windshield, and t represents the total time length of the ultrasonic wave passing through the target windshield;

[0107] Solving the first set of equations to obtain the second time length;

[0108] The crack depth data is determined according to the second time length and a reference propagation speed of the ultrasonic wave in the air.

[0109] In the present application, refer to Figure 7 , Figure 7 A schematic diagram showing a crack on the first surface of the organic glass layer is shown. If the target surface is the first surface of the organic glass layer, the thickness of the organic glass layer through which the ultrasonic wave passes can be expressed as:

[0110] H2=v0*t 21 +v2*t 22

[0111] Among them, v0*t 21 The result is the thickness H of the crack in the organic glass layer. 21 , v2*t 22 The result is the propagation distance H of the ultrasonic wave in the organic glass layer except for the cracks. 22 .

[0112] It can be understood that when cracks appear in the organic glass layer, the total time t for the ultrasonic wave to pass through the entire target windshield is relative to the total reference time t for passing through the template windshield. 总 will change, and the change is caused by the time spent passing through the organic glass layer, which can be expressed by the formula:

[0113] t 21 +t22 -t2=t 总 -t

[0114] Due to the thickness H2 of the organic glass layer, the second propagation speed v2 of the ultrasonic wave in the organic glass layer, the reference propagation speed v0 of the ultrasonic wave in the air, the second reference time t2 of the ultrasonic wave passing through the organic glass layer of the template windshield, and the total reference time t 总 , the total time t of the ultrasonic wave passing through the target windshield can be directly obtained. Therefore, the second time t can be calculated by combining these two formulas. 21 , and then the thickness H of the crack in the organic glass layer can be determined 21 , that is, crack depth data.

[0115] It should be noted that when the target surface is the second surface of the organic glass layer, the calculation strategy is the same as that for the first surface. It is only necessary to adjust the characters corresponding to the thickness of the cracked part and the thickness of the non-cracked part in the organic glass layer, which will not be elaborated here.

[0116] Specifically, in some embodiments, if the target surface is the second surface of the second inorganic glass layer, the third thickness data of the second inorganic glass layer, the third propagation speed of the ultrasonic wave in the second inorganic glass layer, the first reference time length of the ultrasonic wave passing through the first inorganic glass layer, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, and the total time length of the ultrasonic wave passing through the target windshield are obtained; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks;

[0117] Calculate the total duration minus the difference between the first reference duration and the second reference duration to obtain a fourth duration;

[0118] Obtain fourth thickness data according to the product of the fourth time length and the third propagation speed;

[0119] The difference between the third thickness data and the fourth thickness data is calculated to obtain the crack depth data.

[0120] In the present application, refer to Figure 8 , Figure 8 A schematic diagram showing a crack on the second surface of the second inorganic glass layer is shown. If the target surface is the second surface of the second inorganic glass layer, then the ultrasonic wave has no reflection surface after passing through the crack, and the total time t for the ultrasonic wave to pass through the target windshield does not include the time for passing through the crack, and the crack depth data can be calculated by the following formula:

[0121] H 32 =H3-v3*(t-t1-t2)

[0122] In the formula, H 32 represents the crack depth data of the crack on the second surface of the second inorganic glass layer, H3 represents the thickness of the second inorganic glass layer, v3 represents the third propagation speed of the ultrasonic wave in the second inorganic glass layer, t represents the total time of the ultrasonic wave passing through the target windshield, t1 represents the first reference time of the ultrasonic wave passing through the first inorganic glass layer of the template windshield, t2 represents the second reference time of the ultrasonic wave passing through the organic glass layer of the template windshield, v3*(t-t1-t2) is Figure 7 Medium H 31 Length, which is the fourth thickness data.

[0123] The present application also provides a detection and modeling device for aircraft windshield cracks, the device comprising:

[0124] A detection unit, used for performing crack detection on a target windshield by using ultrasonic detection technology;

[0125] a processing unit, configured to determine crack area and crack depth data on the target windshield if cracks exist on the target windshield;

[0126] An identification unit is used to collect overhead image data corresponding to the crack area, input the overhead image data and the crack depth data into a trained machine learning model, identify the crack projection position through the machine learning model, and obtain a corresponding crack projection position identification result;

[0127] The integration unit is used to model the crack of the target windshield according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

[0128] Understandably, Figure 2 The contents of the embodiment of the detection modeling method for a crack in an aircraft windshield are applicable to the embodiment of the detection modeling device for a crack in an aircraft windshield. The functions specifically implemented by the embodiment of the detection modeling device for a crack in an aircraft windshield are similar to those of the embodiment of the detection modeling device for a crack in an aircraft windshield. Figure 2 The detection modeling method for a crack in an aircraft windshield is the same as the embodiment shown in FIG. Figure 2 The beneficial effects achieved by the embodiment of the aircraft windshield crack detection modeling method shown are also the same.

[0129] Reference Fig. 9 , the embodiment of the present application further discloses a computer device, including:

[0130] at least one processor 901;

[0131] At least one memory 902, used to store at least one program;

[0132] When at least one program is executed by at least one processor 901, at least one processor 901 implements the following Figure 2 An embodiment of a detection modeling method for cracks in an aircraft windshield is shown.

[0133] It is understandable that if Figure 2 The contents of the embodiment of the detection modeling method for aircraft windshield cracks shown in the figure are applicable to the embodiment of the computer device. The functions specifically implemented by the embodiment of the computer device are similar to those in the embodiment of the figure. Figure 2 The detection modeling method for a crack in an aircraft windshield is the same as the embodiment shown in FIG. 1 , and the beneficial effects achieved are the same as those of FIG. Figure 2 The beneficial effects achieved by the embodiment of the aircraft windshield crack detection modeling method shown are also the same.

[0134] The present application also discloses a computer-readable storage medium in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the following Figure 2 An embodiment of a detection modeling method for cracks in an aircraft windshield is shown.

[0135] It is understandable that if Figure 2 The contents of the embodiment of the detection modeling method for aircraft windshield cracks shown in the figure are applicable to the embodiment of the computer-readable storage medium. The functions specifically implemented by the embodiment of the computer-readable storage medium are similar to those in the embodiment of the invention. Figure 2 The detection modeling method for a crack in an aircraft windshield is the same as the embodiment shown in FIG. 1 , and the beneficial effects achieved are the same as those of FIG. Figure 2 The beneficial effects achieved by the embodiment of the aircraft windshield crack detection modeling method shown are also the same.

[0136] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0137] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical system and / or software module, or one or more functions and / or features can be implemented in a separate physical system or software module. It can also be understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the system disclosed herein, the actual implementation of the module will be understood within the conventional techniques of engineers. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It can also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0138] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0139] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, system or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, system or device and execute the instructions), or in conjunction with these instruction execution systems, systems or devices. For the purpose of this specification, "computer-readable medium" can be any system that can contain, store, communicate, propagate or transport a program for use by an instruction execution system, system or device, or in conjunction with these instruction execution systems, systems or devices.

[0140] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic systems), a portable computer disk case (magnetic systems), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic system, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0141] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0142] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0143] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0144] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

[0145] In the description of this specification, the description with reference to the terms "one embodiment", "another embodiment" or "certain embodiments" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0146] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A detection modeling method for aircraft windshield cracks, characterized in that: The method comprises: Detect cracks on target windshields using ultrasonic detection technology; If cracks exist on the target windshield, determine crack area and crack depth data on the target windshield; Collecting overhead image data corresponding to the crack area, inputting the overhead image data and the crack depth data into a trained machine learning model, identifying the crack projection position through the machine learning model, and obtaining a corresponding crack projection position identification result; The crack of the target windshield is modeled according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

2. The detection modeling method for aircraft windshield cracks according to claim 1 is characterized in that: The target windshield comprises a first inorganic glass layer, a second inorganic glass layer and an organic glass layer; The first surface of the first inorganic glass layer is the outer surface of the target windshield, the second surface of the first inorganic glass layer is in contact with the first surface of the organic glass layer, the second surface of the organic glass layer is in contact with the first surface of the second inorganic glass layer, and the second surface of the second inorganic glass layer is the inner surface of the target windshield.

3. The detection modeling method for aircraft windshield cracks according to claim 2 is characterized in that: The method of detecting cracks on a target windshield by using ultrasonic detection technology includes: Sending ultrasonic waves to any detection area on the target windshield, and receiving echo data corresponding to the ultrasonic waves; If the echo data is disordered, determining that the target windshield has a crack in the detection area; The target surface where the crack is located is determined according to the time node at which the echo data is disturbed.

4. The detection modeling method for aircraft windshield cracks according to claim 3 is characterized in that: Determining crack depth data on the target windshield includes: If the target surface is the first surface of the first inorganic glass layer, obtaining a first time duration corresponding to the propagation of the ultrasonic wave in the crack on the first surface of the first inorganic glass layer; The crack depth data is determined according to the product of the first time length and a reference propagation speed of the ultrasonic wave in the air.

5. The detection modeling method for aircraft windshield cracks according to claim 3 is characterized in that: Determining crack depth data on the target windshield includes: If the target surface is the first surface of the organic glass layer, obtain the second thickness data of the organic glass layer, the second propagation speed of the ultrasonic wave in the organic glass layer, the reference propagation speed of the ultrasonic wave in the air, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, the total reference time length of the ultrasonic wave passing through the template windshield, and the total time length of the ultrasonic wave passing through the target windshield; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks; A first set of equations is established, wherein the formula of the first set of equations is: H2=v0*t 21 +v2*t 22 t 21 +t 22 -t2=t 总 -t Wherein, H2 represents the second thickness data of the organic glass layer, v0 represents the reference propagation speed of the ultrasonic wave in the air, and t 21 represents the second time duration corresponding to the ultrasonic wave propagating in the crack on the first surface of the organic glass layer, v2 represents the second propagation speed of the ultrasonic wave in the organic glass layer, t 22 represents the third time duration corresponding to the propagation of the ultrasonic wave in the organic glass layer except for the cracks, t2 represents the second reference time duration of the ultrasonic wave passing through the organic glass layer of the template windshield, t 总 represents the total reference time length of the ultrasonic wave passing through the template windshield, and t represents the total time length of the ultrasonic wave passing through the target windshield; Solving the first set of equations to obtain the second time length; The crack depth data is determined according to the second time length and a reference propagation speed of the ultrasonic wave in the air.

6. The aircraft windshield crack detection modeling method according to claim 3, characterized in that: Determining crack depth data on the target windshield includes: If the target surface is the second surface of the second inorganic glass layer, obtain the third thickness data of the second inorganic glass layer, the third propagation speed of the ultrasonic wave in the second inorganic glass layer, the first reference time length of the ultrasonic wave passing through the first inorganic glass layer, the second reference time length of the ultrasonic wave passing through the organic glass layer of the template windshield, and the total time length of the ultrasonic wave passing through the target windshield; wherein the template windshield is a windshield of the same model as the target windshield and has no cracks; Calculate the total duration minus the difference between the first reference duration and the second reference duration to obtain a fourth duration; Obtain fourth thickness data according to the product of the fourth time length and the third propagation speed; The difference between the third thickness data and the fourth thickness data is calculated to obtain the crack depth data.

7. A detection modeling device for aircraft windshield cracks, characterized in that: The device comprises: A detection unit, used for performing crack detection on a target windshield by using ultrasonic detection technology; a processing unit, configured to determine crack area and crack depth data on the target windshield if cracks exist on the target windshield; An identification unit is used to collect overhead image data corresponding to the crack area, input the overhead image data and the crack depth data into a trained machine learning model, identify the crack projection position through the machine learning model, and obtain a corresponding crack projection position identification result; The integration unit is used to model the crack of the target windshield according to the standard module data corresponding to the target windshield, the crack area, the crack depth data and the crack projection position identification result to obtain a modeling result.

8. The aircraft windshield crack detection modeling device according to claim 7, characterized in that: The target windshield comprises a first inorganic glass layer, a second inorganic glass layer and an organic glass layer; The first surface of the first inorganic glass layer is the outer surface of the target windshield, the second surface of the first inorganic glass layer is in contact with the first surface of the organic glass layer, the second surface of the organic glass layer is in contact with the first surface of the second inorganic glass layer, and the second surface of the second inorganic glass layer is the inner surface of the target windshield.

9. A computer device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the aircraft windshield crack detection modeling method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement a detection and modeling method for aircraft windshield cracks as described in any one of claims 1 to 6 when executed by the processor.

Images